arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 217 records · Page 12Linked to original sources

arXiv2025

CogniPair: From LLM Chatbots to Conscious AI Agents -- GNWT-Based Multi-Agent Digital Twins for Social Pairing -- Dating & Hiring Applications

Current large language model (LLM) agents lack authentic human psychological processes necessary for genuine digital twins and social AI applications. To address this limitation, we present a computational implementation of Global Workspace Theory (GNWT) that integrates human cognitive architecture principles into LLM agents, creating specialized sub-agents for emotion, memory, social norms, planning, and goal-tracking coordinated through a global workspace mechanism. However, authentic digital twins require accurate personality initialization. We therefore develop a novel adventure-based personality test that evaluates true personality through behavioral choices within interactive scenarios, bypassing self-presentation bias found in traditional assessments. Building on these innovations, our CogniPair platform enables digital twins to engage in realistic simulated dating interactions and job interviews before real encounters, providing bidirectional cultural fit assessment for both romantic compatibility and workplace matching. Validation using 551 GNWT-Agents and Columbia University Speed Dating dataset demonstrates 72% correlation with human attraction patterns, 77.8% match prediction accuracy, and 74% agreement in human validation studies. This work advances psychological authenticity in LLM agents and establishes a foundation for intelligent dating platforms and HR technology solutions.

cs.AI↗

arXiv2025

Augur: Modeling Covariate Causal Associations in Time Series via Large Language Models

Large language models (LLM) have emerged as a promising avenue for time series forecasting, offering the potential to integrate multimodal data. However, existing LLM-based approaches face notable limitations-such as marginalized role in model architectures, reliance on coarse statistical text prompts, and lack of interpretability. In this work, we introduce Augur, a fully LLM driven time series forecasting framework that exploits LLM causal reasoning to discover and use directed causal associations among covariates. Augur uses a two stage teacher student architecture where a powerful teacher LLM infers a directed causal graph from time series using heuristic search together with pairwise causality testing. A lightweight student agent then refines the graph and fine tune on high confidence causal associations that are encoded as rich textual prompts to perform forecasting. This design improves predictive accuracy while yielding transparent, traceable reasoning about variable interactions. Extensive experiments on real-world datasets with 26 baselines demonstrate that Augur achieves competitive performance and robust zero-shot generalization.

cs.AI↗

arXiv2025

Water induced bandgap engineering in nanoribbons of hexagonal boron nitride

Different from hexagonal boron nitride (hBN) sheets, the bandgap of hBN nanoribbons (BNNRs) can be changed by spatial/electrostatic confinement. It has been predicted that a transverse electric field can narrow the bandgap and even cause an insulator-metal transition in BNNRs. However, experimentally introducing an overhigh electric field across the BNNR remains challenging. Here, we theoretically and experimentally demonstrate that water adsorption greatly reduces bandgap of zigzag oriented BNNRs (zBNNRs). Ab initio calculations show that water adsorbed beside the BNNR induces a transverse equivalent electric field of over 2 V/nm thereby reducing its bandgap. Field effect transistors were successfully fabricated from zBNNRs with different widths. The conductance of zBNNRs with adsorbates of water could be tuned over 3 orders in magnitude via electrical field modulation at room temperature. Furthermore, photocurrent response measurements were taken to determine the optical bandgap in zBNNR. Wider zBNNRs exhibit a bandgap down to 1.17 eV. This study yields fundamental insights in new routes toward realizing electronic/optoelectronic devices and circuits based on hexagonal boron nitride.

cond-mat.mtrl-sci↗

arXiv2025

MVS-TTA: Test-Time Adaptation for Multi-View Stereo via Meta-Auxiliary Learning

Recent learning-based multi-view stereo (MVS) methods are data-driven and have achieved remarkable progress due to large-scale training data and advanced architectures. However, their generalization remains sub-optimal due to fixed model parameters trained on limited training data distributions. In contrast, optimization-based methods enable scene-specific adaptation but lack scalability and require costly per-scene optimization. In this paper, we propose MVS-TTA, an efficient test-time adaptation (TTA) framework that enhances the adaptability of learning-based MVS methods by bridging these two paradigms. Specifically, MVS-TTA employs a self-supervised, cross-view consistency loss as an auxiliary task to guide inference-time adaptation. We introduce a meta-auxiliary learning strategy to train the model to benefit from auxiliary-task-based updates explicitly. Our framework is model-agnostic and can be applied to a wide range of MVS methods with minimal architectural changes. Extensive experiments on standard datasets (DTU, BlendedMVS) and a challenging cross-dataset generalization setting demonstrate that MVS-TTA consistently improves performance, even when applied to state-of-the-art MVS models. To our knowledge, this is the first attempt to integrate optimization-based test-time adaptation into learning-based MVS using meta-learning. The code will be available at https://github.com/mart87987-svg/MVS-TTA.

cs.CV↗

arXiv2025

Agent-SAMA: State-Aware Mobile Assistant

Mobile Graphical User Interface (GUI) agents aim to autonomously complete tasks within or across apps based on user instructions. While recent Multimodal Large Language Models (MLLMs) enable these agents to interpret UI screens and perform actions, existing agents remain fundamentally reactive. They reason over the current UI screen but lack a structured representation of the app navigation flow, limiting GUI agents' ability to understand execution context, detect unexpected execution results, and recover from errors. We introduce Agent-SAMA, a state-aware multi-agent framework that models app execution as a Finite State Machine (FSM), treating UI screens as states and user actions as transitions. Agent-SAMA implements four specialized agents that collaboratively construct and use FSMs in real time to guide task planning, execution verification, and recovery. We evaluate Agent-SAMA on two types of benchmarks: cross-app (Mobile-Eval-E, SPA-Bench) and mostly single-app (AndroidWorld). On Mobile-Eval-E, Agent-SAMA achieves an 84.0% success rate and a 71.9% recovery rate. On SPA-Bench, it reaches an 80.0% success rate with a 66.7% recovery rate. Compared to prior methods, Agent-SAMA improves task success by up to 12% and recovery success by 13.8%. On AndroidWorld, Agent-SAMA achieves a 63.7% success rate, outperforming the baselines. Our results demonstrate that structured state modeling enhances robustness and can serve as a lightweight, model-agnostic memory layer for future GUI agents.

cs.AI↗

arXiv2025

FastDriveVLA: Efficient End-to-End Driving via Plug-and-Play Reconstruction-based Token Pruning

Vision-Language-Action (VLA) models have demonstrated significant potential in complex scene understanding and action reasoning, leading to their increasing adoption in end-to-end autonomous driving systems. However, the long visual tokens of VLA models greatly increase computational costs. Current visual token pruning methods in Vision-Language Models (VLM) rely on either visual token similarity or visual-text attention, but both have shown poor performance in autonomous driving scenarios. Given that human drivers concentrate on relevant foreground areas while driving, we assert that retaining visual tokens containing this foreground information is essential for effective decision-making. Inspired by this, we propose FastDriveVLA, a novel reconstruction-based vision token pruning framework designed specifically for autonomous driving. FastDriveVLA includes a plug-and-play visual token pruner called ReconPruner, which prioritizes foreground information through MAE-style pixel reconstruction. A novel adversarial foreground-background reconstruction strategy is designed to train ReconPruner for the visual encoder of VLA models. Once trained, ReconPruner can be seamlessly applied to different VLA models with the same visual encoder without retraining. To train ReconPruner, we also introduce a large-scale dataset called nuScenes-FG, consisting of 241K image-mask pairs with annotated foreground regions. Our approach achieves state-of-the-art results on the nuScenes open-loop planning benchmark across different pruning ratios.

cs.CV↗

arXiv2025

Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis

Homeostatic mechanisms play a crucial role in maintaining optimal functionality within the neural circuits of the brain. By regulating physiological and biochemical processes, these mechanisms ensure the stability of an organism's internal environment, enabling it to better adapt to external changes. Among these mechanisms, the Bienenstock, Cooper, and Munro (BCM) theory has been extensively studied as a key principle for maintaining the balance of synaptic strengths in biological systems. Despite the extensive development of spiking neural networks (SNNs) as a model for bionic neural networks, no prior work in the machine learning community has integrated biologically plausible BCM formulations into SNNs to provide homeostasis. In this study, we propose a Dynamic Weight Adaptation Mechanism (DWAM) for SNNs, inspired by the BCM theory. DWAM can be integrated into the host SNN, dynamically adjusting network weights in real time to regulate neuronal activity, providing homeostasis to the host SNN without any fine-tuning. We validated our method through dynamic obstacle avoidance and continuous control tasks under both normal and specifically designed degraded conditions. Experimental results demonstrate that DWAM not only enhances the performance of SNNs without existing homeostatic mechanisms under various degraded conditions but also further improves the performance of SNNs that already incorporate homeostatic mechanisms.

cs.NE↗

arXiv2025

Bidirectional Image-Event Guided Fusion Framework for Low-Light Image Enhancement

Under extreme low-light conditions, frame-based cameras suffer from severe detail loss due to limited dynamic range. Recent studies have introduced event cameras for event-guided low-light image enhancement. However, existing approaches often overlook the flickering artifacts and structural discontinuities caused by dynamic illumination changes and event sparsity. To address these challenges, we propose BiLIE, a Bidirectional image-event guided fusion framework for Low-Light Image Enhancement, which achieves mutual guidance and complementary enhancement between the two modalities. First, to highlight edge details, we develop a Dynamic Adaptive Filtering Enhancement (DAFE) module that performs adaptive high-pass filtering on event representations to suppress flickering artifacts and preserve high-frequency information under varying illumination. Subsequently, we design a Bidirectional Guided Awareness Fusion (BGAF) mechanism, which achieves breakpoint-aware restoration from images to events and structure-aware enhancement from events to images through a two-stage attention mechanism, establishing cross-modal consistency, thereby producing a clear, smooth, and structurally intact fused representation. Moreover, recognizing that existing datasets exhibit insufficient ground-truth fidelity and color accuracy, we construct a high-quality low-light image-event dataset (RELIE) via a reliable ground truth refinement scheme. Extensive experiments demonstrate that our method outperforms existing approaches on both the RELIE and LIE datasets. Notably, on RELIE, BiLIE exceeds the state-of-the-art by 0.81dB in PSNR and shows significant advantages in edge restoration, color fidelity, and noise suppression.

cs.CV↗

arXiv2025

Capacity Estimation of Lithium-ion Batteries Using Invariance Property in Open Circuit Voltage Relationship

Lithium-ion (Li-ion) batteries are ubiquitous in electric vehicles (EVs) as efficient energy storage devices. The reliable operation of Li-ion batteries depends critically on the accurate estimation of battery capacity. However, conventional estimation methods require extensive training datasets from costly battery tests for modeling, and a full cycle of charge and discharge is often needed to estimate the capacity. To overcome these limitations, we propose a novel capacity estimation method that leverages only one cycle of the open-circuit voltage (OCV) test in modeling and allows for estimating the capacity from partial charge or discharge data. Moreover, by applying it with OCV identification algorithms, we can estimate the capacity from dynamic discharge data without requiring dedicated data collection tests. We observed an invariance property in the OCV versus state of charge relationship across aging cycles. Leveraging this invariance, the proposed method estimates the capacity by solving an OCV alignment problem using only the OCV and the discharge capacity data from the battery. Simulation results demonstrate the method's efficacy, achieving a mean absolute relative error of 0.85\% in capacity estimation across 12 samples from 344 aging cycles.

eess.SY↗

arXiv2025

ArchPilot: A Proxy-Guided Multi-Agent Approach for Machine Learning Engineering

Recent LLM-based agents have demonstrated strong capabilities in automated ML engineering. However, they heavily rely on repeated full training runs to evaluate candidate solutions, resulting in significant computational overhead, limited scalability to large search spaces, and slow iteration cycles. To address these challenges, we introduce ArchPilot, a multi-agent system that integrates architecture generation, proxy-based evaluation, and adaptive search into a unified framework. ArchPilot consists of three specialized agents: an orchestration agent that coordinates the search process using a Monte Carlo Tree Search (MCTS)-inspired novel algorithm with a restart mechanism and manages memory of previous candidates; a generation agent that iteratively generates, improves, and debugs candidate architectures; and an evaluation agent that executes proxy training runs, generates and optimizes proxy functions, and aggregates the proxy scores into a fidelity-aware performance metric. This multi-agent collaboration allows ArchPilot to prioritize high-potential candidates with minimal reliance on expensive full training runs, facilitating efficient ML engineering under limited budgets. Experiments on MLE-Bench demonstrate that ArchPilot outperforms SOTA baselines such as AIDE and ML-Master, validating the effectiveness of our multi-agent system.

cs.AI↗

arXiv2025

Cost Reducing Adiabatic Compressed Air Energy Storage for Long Duration Energy Storage Applications

Long-duration energy storage (LDES) is vital for decarbonizing the energy system but faces economic challenges, including high upfront costs, low trading frequency, and limited revenue in current electricity markets. Compressed Air Energy Storage (CAES) is a promising LDES solution, though its economic viability, especially for long storage durations beyond lithium-ion battery capabilities, remains unclear. To address this, here we compiled and analyzed a global emerging adiabatic CAES cost database, showing a continuous cost reduction with an experience rate of 15% as capacities scaled from 10MW to 100MW. Our lifecycle discounted cash flow analysis suggests that adiabatic CAES could achieve economic viability for 10-100 hour storage durations, particularly with optimal geological siting to lower storage costs. This economically viable LDES option will enable large-scale grid balancing and support renewable integration over multi-day periods, making it a valuable asset for advancing deep decarbonization of energy systems.

physics.soc-ph↗

arXiv2025

LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling

Diffusion models excel at joint pixel sampling for image generation but lack efficient training-free methods for partial conditional sampling (e.g., inpainting with known pixels). Prior work typically formulates this as an intractable inverse problem, relying on coarse variational approximations, heuristic losses requiring expensive backpropagation, or slow stochastic sampling. These limitations preclude: (1) accurate distributional matching in inpainting results, (2) efficient inference modes without gradient, (3) compatibility with fast ODE-based samplers. To address these limitations, we propose LanPaint: a training-free, asymptotically exact partial conditional sampling methods for ODE-based and rectified flow diffusion models. By leveraging carefully designed Langevin dynamics, LanPaint enables fast, backpropagation-free Monte Carlo sampling. Experiments demonstrate that our approach achieves superior performance with precise partial conditioning and visually coherent inpainting across diverse tasks.

eess.IV↗

arXiv2025

Kagome on beta-Sb with valley-hot Berry curvature and tunable intrinsic SHC

Large-area, single-crystalline antimonene polygonal domains self-assemble on Al(111) at room temperature without forming an interfacial alloy layer by MBE. Beyond the beta-Sb phase,with increasing deposition, once the beta-Sb coverage surpasses a threshold, we observe a previously unreported kagome-Sb overlayer. STM height maps and line profiles track a phase evolution from an enlarged-period honeycomb to a close-packed layer and ultimately a kagome lattice. XPS peak not only shows resolves a time-dependent redistribution of Sb-related components that quantitatively mirrors the STM-observed phase sequence, but also revals the substrate core levels remain unchanged, ruling out interfacial alloying throughout growth. ARPES of beta-Sb resolves a Dirac-like crossing at Gamma around -1.4 eV, in agreement with first-principles calculations. Although beta-Sb is Z2-trivial and the heterostructure is metallic, Wannier-based calculations reveal valley-contrasting Berry-curvature hotspots, yielding an intrinsic spin Hall conductivity that is strongly Fermi-level dependent. These results demonstrate a reproducible kagome-Sb/beta-Sb heterophase interface and uncover a controllable spin-orbit-driven response in a homoelemental 2D system.

cond-mat.mtrl-sci↗

arXiv2025

One Stone with Two Birds: A Null-Text-Null Frequency-Aware Diffusion Models for Text-Guided Image Inpainting

Text-guided image inpainting aims at reconstructing the masked regions as per text prompts, where the longstanding challenges lie in the preservation for unmasked regions, while achieving the semantics consistency between unmasked and inpainted masked regions. Previous arts failed to address both of them, always with either of them to be remedied. Such facts, as we observed, stem from the entanglement of the hybrid (e.g., mid-and-low) frequency bands that encode varied image properties, which exhibit different robustness to text prompts during the denoising process. In this paper, we propose a null-text-null frequency-aware diffusion models, dubbed \textbf{NTN-Diff}, for text-guided image inpainting, by decomposing the semantics consistency across masked and unmasked regions into the consistencies as per each frequency band, while preserving the unmasked regions, to circumvent two challenges in a row. Based on the diffusion process, we further divide the denoising process into early (high-level noise) and late (low-level noise) stages, where the mid-and-low frequency bands are disentangled during the denoising process. As observed, the stable mid-frequency band is progressively denoised to be semantically aligned during text-guided denoising process, which, meanwhile, serves as the guidance to the null-text denoising process to denoise low-frequency band for the masked regions, followed by a subsequent text-guided denoising process at late stage, to achieve the semantics consistency for mid-and-low frequency bands across masked and unmasked regions, while preserve the unmasked regions. Extensive experiments validate the superiority of NTN-Diff over the state-of-the-art diffusion models to text-guided diffusion models. Our code can be accessed from https://github.com/htyjers/NTN-Diff.

cs.CV↗

arXiv2025

Extreme Strong Branching for QCQPs

For mixed-integer programs (MIPs), strong branching is a highly effective variable selection method to reduce the number of nodes in the branch-and-bound algorithm. Extending it to nonlinear problems is conceptually simple but practically limited. Branching on a binary variable fixes the variable to 0 or 1, whereas branching on a continuous variable requires an additional decision to choose a branching point. Previous extensions of strong branching predefine this point and then solve $2n$ relaxations where $n$ is the number of candidate variables to branch. We propose extreme strong branching, which evaluates multiple branching points per variable and jointly selects both the branching variable and point based on the objective value improvement. This approach resembles the success of strong branching for MIPs while additionally exploiting bound tightening as a byproduct. For certain types of quadratically constrained quadratic programs (QCQPs), computational experiments show that the extreme strong branching rule outperforms existing commercial solvers.

math.OC↗

arXiv2025

From Quarter to All: Accelerating Speculative LLM Decoding via Floating-Point Exponent Remapping and Parameter Sharing

Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to the full model. Speculative decoding remains lossless but typically incurs extra overheads. We propose SPEQ, an algorithm-hardware co-designed speculative decoding method that uses part of the full-model weight bits to form a quantized draft model, thereby eliminating additional training or storage overhead. A reconfigurable processing element array enables efficient execution of both the draft and verification passes. Experimental results across 15 LLMs and tasks demonstrate that SPEQ achieves speedups of 2.07x, 1.53x, and 1.45x compared over FP16, Olive, and Tender, respectively.

cs.AR↗

arXiv2025

Deep Self-Evolving Reasoning

Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprietary models to solve Olympiad-level problems, their effectiveness hinges on strong, reliable verification and correction capabilities, which remain fragile in open-weight, smaller-scale models. This work demonstrates that even with weak verification and refinement capabilities on hard tasks, the reasoning limits of such models can be substantially extended through a probabilistic paradigm we call Deep Self-Evolving Reasoning (DSER). We conceptualize iterative reasoning as a Markov chain, where each step represents a stochastic transition in the solution space. The key insight is that convergence to a correct solution is guaranteed as long as the probability of improvement marginally exceeds that of degradation. By running multiple long-horizon, self-evolving processes in parallel, DSER amplifies these small positive tendencies, enabling the model to asymptotically approach correct answers. Empirically, we apply DSER to the DeepSeek-R1-0528-Qwen3-8B model. On the challenging AIME 2024-2025 benchmark, DSER solves 5 out of 9 previously unsolvable problems and boosts overall performance, enabling this compact model to surpass the single-turn accuracy of its 600B-parameter teacher through majority voting. Beyond its immediate utility for test-time scaling, the DSER framework serves to diagnose the fundamental limitations of current open-weight reasoners. By clearly delineating their shortcomings in self-verification, refinement, and stability, our findings establish a clear research agenda for developing next-generation models with powerful, intrinsic self-evolving capabilities.

cs.CL↗

arXiv2025

STARK: Strategic Team of Agents for Refining Kernels

The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory hierarchies, thread scheduling, and hardware-specific characteristics. While recent advances in large language models (LLMs) provide new opportunities for automated code generation, existing approaches largely treat LLMs as single-shot generators or naive refinement tools, limiting their effectiveness in navigating the irregular kernel optimization landscape. We introduce an LLM agentic framework for GPU kernel optimization that systematically explores the design space through multi-agent collaboration, grounded instruction, dynamic context management, and strategic search. This framework mimics the workflow of expert engineers, enabling LLMs to reason about hardware trade-offs, incorporate profiling feedback, and refine kernels iteratively. We evaluate our approach on KernelBench, a benchmark for LLM-based kernel optimization, and demonstrate substantial improvements over baseline agents: our system produces correct solutions where baselines often fail, and achieves kernels with up to 16x faster runtime performance. These results highlight the potential of agentic LLM frameworks to advance fully automated, scalable GPU kernel optimization.

cs.AI↗